\documentclass[10pt,a4paper]{article}

% Packages
\usepackage{fancyhdr}           % For header and footer
\usepackage{multicol}           % Allows multicols in tables
\usepackage{tabularx}           % Intelligent column widths
\usepackage{tabulary}           % Used in header and footer
\usepackage{hhline}             % Border under tables
\usepackage{graphicx}           % For images
\usepackage{xcolor}             % For hex colours
%\usepackage[utf8x]{inputenc}    % For unicode character support
\usepackage[T1]{fontenc}        % Without this we get weird character replacements
\usepackage{colortbl}           % For coloured tables
\usepackage{setspace}           % For line height
\usepackage{lastpage}           % Needed for total page number
\usepackage{seqsplit}           % Splits long words.
%\usepackage{opensans}          % Can't make this work so far. Shame. Would be lovely.
\usepackage[normalem]{ulem}     % For underlining links
% Most of the following are not required for the majority
% of cheat sheets but are needed for some symbol support.
\usepackage{amsmath}            % Symbols
\usepackage{MnSymbol}           % Symbols
\usepackage{wasysym}            % Symbols
%\usepackage[english,german,french,spanish,italian]{babel}              % Languages

% Document Info
\author{josi68}
\pdfinfo{
  /Title (introduction-to-r.pdf)
  /Creator (Cheatography)
  /Author (josi68)
  /Subject (Introduction to R Cheat Sheet)
}

% Lengths and widths
\addtolength{\textwidth}{6cm}
\addtolength{\textheight}{-1cm}
\addtolength{\hoffset}{-3cm}
\addtolength{\voffset}{-2cm}
\setlength{\tabcolsep}{0.2cm} % Space between columns
\setlength{\headsep}{-12pt} % Reduce space between header and content
\setlength{\headheight}{85pt} % If less, LaTeX automatically increases it
\renewcommand{\footrulewidth}{0pt} % Remove footer line
\renewcommand{\headrulewidth}{0pt} % Remove header line
\renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit
% This two commands together give roughly
% the right line height in the tables
\renewcommand{\arraystretch}{1.3}
\onehalfspacing

% Commands
\newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour
\newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols
\newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns
\newcommand{\tn}{\tabularnewline} % Required as custom column type in use

% Font and Colours
\definecolor{HeadBackground}{HTML}{333333}
\definecolor{FootBackground}{HTML}{666666}
\definecolor{TextColor}{HTML}{333333}
\definecolor{DarkBackground}{HTML}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\renewcommand{\familydefault}{\sfdefault}
\color{TextColor}

% Header and Footer
\pagestyle{fancy}
\fancyhead{} % Set header to blank
\fancyfoot{} % Set footer to blank
\fancyhead[L]{
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{C}
    \SetRowColor{DarkBackground}
    \vspace{-7pt}
    {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent
        \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}}
    }
\end{tabulary}
\columnbreak
\begin{tabulary}{11cm}{L}
    \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{Introduction to R Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{josi68} via \textcolor{DarkBackground}{\uline{cheatography.com/197242/cs/41550/}}}
\end{tabulary}
\end{multicols}}

\fancyfoot[L]{ \footnotesize
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{LL}
  \SetRowColor{FootBackground}
  \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}}  \\
  \vspace{-2pt}josi68 \\
  \uline{cheatography.com/josi68} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Not Yet Published.\\
   Updated 4th December, 2023.\\
   Page {\thepage} of \pageref{LastPage}.
\end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}}  \\
  \SetRowColor{white}
  \vspace{-5pt}
  %\includegraphics[width=48px,height=48px]{dave.jpeg}
  Measure your website readability!\\
  www.readability-score.com
\end{tabulary}
\end{multicols}}




\begin{document}
\raggedright
\raggedcolumns

% Set font size to small. Switch to any value
% from this page to resize cheat sheet text:
% www.emerson.emory.edu/services/latex/latex_169.html
\footnotesize % Small font.

\begin{multicols*}{3}

\begin{tabularx}{5.377cm}{x{4.32999 cm} p{0.64701 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Arithmetics}}  \tn
% Row 0
\SetRowColor{LightBackground}
Addition & + \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
Subtraction & - \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
Multiplication & * \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
Division & / \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
Modulo & \%\% \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
Exponentiation & \textasciicircum{} \tn 
% Row Count 6 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{{\emph{Modulo returns the remainder of the division of the number to the left by the number on its right, for example 5 modulo 3 or 5 \%\% 3 is 2.}}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{4.4793 cm} p{0.4977 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Comparison operators}}  \tn
% Row 0
\SetRowColor{LightBackground}
Less than & \textless{} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
More than & \textgreater{} \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
Less than or equal to & \textless{}= \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
Greater than or equal to & \textgreater{}= \tn 
% Row Count 4 (+ 1)
% Row 4
\SetRowColor{LightBackground}
Equal to each other & == \tn 
% Row Count 5 (+ 1)
% Row 5
\SetRowColor{white}
Not equal to each other & != \tn 
% Row Count 6 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Selecting by comparison}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\# Poker and roulette winnings from Monday to Friday: \newline poker\_vector \textless{}- c(140, -50, 20, -120, 240) \newline roulette\_vector \textless{}- c(-24, -50, 100, -350, 10) \newline days\_vector \textless{}- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday") \newline names(poker\_vector) \textless{}- days\_vector \newline names(roulette\_vector) \textless{}- days\_vector \newline  \newline \# Which days did you make money on roulette? \newline selection\_vector \textless{}- roulette\_vector \textgreater{} 0 \newline  \newline \# Select from roulette\_vector these days \newline roulette\_winning\_days \textless{}- roulette\_vector{[}selection\_vector{]}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{1.78503 cm} x{1.51041 cm} x{1.28156 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{3}{x{5.377cm}}{\bf\textcolor{white}{Data Types}}  \tn
% Row 0
\SetRowColor{LightBackground}
Decimal values & 4.5 & Numerics \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
Whole numbers & 4 & Integers \tn 
% Row Count 2 (+ 1)
% Row 2
\SetRowColor{LightBackground}
Boolean values & TRUE / FALSE & Logical \tn 
% Row Count 3 (+ 1)
% Row 3
\SetRowColor{white}
Text / String & "Text" & Characters \tn 
% Row Count 4 (+ 1)
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\SetRowColor{LightBackground}
\mymulticolumn{3}{x{5.377cm}}{Show the data type: class({\emph{data}})}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}---}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.04057 cm} x{2.93643 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Lists}}  \tn
% Row 0
\SetRowColor{LightBackground}
Create a list & my\_list \textless{}- list(element1, element2) \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Give names to the list items & my\_list \textless{}- list(name1 = your\_comp1,                  name2 = your\_comp2) \tn 
% Row Count 6 (+ 4)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{\# Adapt list() call to give the components names  \newline my\_list \textless{}- list(vec = my\_vector, \newline                   mat = my\_matrix, \newline                  df = my\_df)   \newline  \newline \#or if the list was alread created  \newline names(my\_list) \textless{}- c("vec", "mat", "df")}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Selecting components in a list}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{One way to select a component is using the numbered position of that component. For example, to "grab" the first component of shining\_list you type \newline % Row Count 3 (+ 3)
shining\_list{[}{[}1{]}{]} \newline % Row Count 4 (+ 1)
A quick way to check this out is typing it in the console. Important to remember: to select elements from vectors, you use single square brackets: {[} {]}. Don't mix them up! \newline % Row Count 8 (+ 4)
You can also refer to the names of the components, with {[}{[} {]}{]} or with the \$ sign. Both will select the data frame representing the reviews: \newline % Row Count 11 (+ 3)
shining\_list{[}{[}"reviews"{]}{]} \newline % Row Count 12 (+ 1)
shining\_list\$reviews \newline % Row Count 13 (+ 1)
Besides selecting components, you often need to select specific elements out of these components. For example, with shining\_list{[}{[}2{]}{]}{[}1{]} you select from the second component, actors (shining\_list{[}{[}2{]}{]}), the first element ({[}1{]}). When you type this in the console, you will see the answer is Jack Nicholson.% Row Count 20 (+ 7)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Vector Basics}}  \tn
% Row 0
\SetRowColor{LightBackground}
Assign value to variable & my\_var \textless{}- 4 \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Numeric vector & numeric\_vector \textless{}- c(1, 10, 49) \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Character\_vector & character\_vector \textless{}- c("a", "b", "c") \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
Boolean vector & boolean\_vector \textless{}- c(TRUE, FALSE, TRUE) \tn 
% Row Count 8 (+ 2)
% Row 4
\SetRowColor{LightBackground}
Naming a vector & \seqsplit{names(numeric\_vector)} \textless{}- c("Jack", "Jill", "Johanna") \tn 
% Row Count 11 (+ 3)
% Row 5
\SetRowColor{white}
Sum of the elements in the vector & sum(vector\_name) \tn 
% Row Count 13 (+ 2)
% Row 6
\SetRowColor{LightBackground}
Select element 3 of the vector & element \textless{}- vector\_name{[}3{]} \tn 
% Row Count 15 (+ 2)
% Row 7
\SetRowColor{white}
Select elements 2, 3, 4, 5 of the vector & elements \textless{}- vector\_name{[}3:5{]} \tn 
% Row Count 17 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Factors}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\# Animals - Turn vector character elements into nominal factors \newline animals\_vector \textless{}- c("Elephant", "Giraffe", "Donkey", "Horse") \newline factor\_animals\_vector \textless{}- factor(animals\_vector) \newline factor\_animals\_vector \newline  \newline \# Temperature - Turn vector character elements into ordinal factors \newline temperature\_vector \textless{}- c("High", "Low", "High","Low", "Medium") \newline factor\_temperature\_vector \textless{}- \seqsplit{factor(temperature\_vector}, order = TRUE, levels = c("Low", "Medium", "High")) \newline factor\_temperature\_vector} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{When factors are ordinal::  \newline order = TRUE  \newline  \newline To give the order of the ordinal factors: \newline levels = c("Low", "Medium", "High"))}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{3.38436 cm} x{1.59264 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Data Frames}}  \tn
% Row 0
\SetRowColor{LightBackground}
Show the first couple of lines & \seqsplit{head(data\_frame)} \tn 
% Row Count 2 (+ 2)
% Row 1
\SetRowColor{white}
Show the last couple of lines & \seqsplit{tail(data:frame)} \tn 
% Row Count 4 (+ 2)
% Row 2
\SetRowColor{LightBackground}
Summarize data frame (min, max, median, quartiles) & \seqsplit{summary(data\_frame)} \tn 
% Row Count 6 (+ 2)
% Row 3
\SetRowColor{white}
Structure (nr. obs, var., names, data type...) & \seqsplit{str(data\_frame)} \tn 
% Row Count 8 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{{\bf{unlike matrixes, df can have different types of data - BUT all variables need to have the same length (unlike for lists)}}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Create data frame from vectors + select values}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\# Definition of vectors \newline name \textless{}- c("Mercury", "Venus", "Earth",  \newline           "Mars", "Jupiter", "Saturn",  \newline           "Uranus", "Neptune") \newline type \textless{}- c("Terrestrial planet",  \newline           "Terrestrial planet",  \newline           "Terrestrial planet",  \newline           "Terrestrial planet", "Gas giant",  \newline           "Gas giant", "Gas giant", "Gas giant") \newline diameter \textless{}- c(0.382, 0.949, 1, 0.532,  \newline               11.209, 9.449, 4.007, 3.883) \newline rotation \textless{}- c(58.64, -243.02, 1, 1.03,  \newline               0.41, 0.43, -0.72, 0.67) \newline rings \textless{}- c(FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, TRUE) \newline  \newline \# Create a data frame from the vectors \newline planets\_df \textless{}- data.frame(name, type, diameter, rotation, rings) \newline  \newline \# Select first 5 values of diameter column \newline planets\_df{[}1:5, "diameter"{]} \newline  \newline \# Select the rings variable from planets\_df \newline rings\_vector \textless{}- planets\_df\$rings \newline  \newline \# Select planets with diameter \textless{} 1 \newline subset(planets\_df, subset = diameter \textless{}1)} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Order the data}}  \tn
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{In data analysis you can sort your data according to a certain variable in the dataset. In R, this is done with the help of the function order(). \newline % Row Count 3 (+ 3)
order() is a function that gives you the ranked position of each element when it is applied on a variable, such as a vector for example: \newline % Row Count 6 (+ 3)
a \textless{}- c(100, 10, 1000) \newline % Row Count 7 (+ 1)
order(a) \newline % Row Count 8 (+ 1)
{[}1{]} 2 1 3 \newline % Row Count 9 (+ 1)
10, which is the second element in a, is the smallest element, so 2 comes first in the output of order(a). 100, which is the first element in a is the second smallest element, so 1 comes second in the output of order(a). \newline % Row Count 14 (+ 5)
This means we can use the output of order(a) to reshuffle a: \newline % Row Count 16 (+ 2)
a{[}order(a){]} \newline % Row Count 17 (+ 1)
{[}1{]}   10  100 1000% Row Count 18 (+ 1)
} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{x{2.4885 cm} x{2.4885 cm} }
\SetRowColor{DarkBackground}
\mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Matrices}}  \tn
% Row 0
\SetRowColor{LightBackground}
Construct Matrix with 3 rows that contain the numbers 1 to 9 & matrix(1:9, byrow = TRUE, nrow = 3) \tn 
% Row Count 3 (+ 3)
% Row 1
\SetRowColor{white}
From Vector to Matrix & Matrix\_names \textless{}- matrix(vector\_name, byrow = TRUE, nrow = 3) \tn 
% Row Count 6 (+ 3)
% Row 2
\SetRowColor{LightBackground}
Totals for each row of a matrix & rowSums(my\_matrix) \tn 
% Row Count 8 (+ 2)
% Row 3
\SetRowColor{white}
Total for each row of a matrix & colSums() \tn 
% Row Count 10 (+ 2)
% Row 4
\SetRowColor{LightBackground}
Adding columns & big matrix \textless{}- cbind(vector1, matrix1) \tn 
% Row Count 12 (+ 2)
% Row 5
\SetRowColor{white}
Adding rows & rbind \tn 
% Row Count 13 (+ 1)
% Row 6
\SetRowColor{LightBackground}
Select all elements of the first column & matrix{[},1{]} \tn 
% Row Count 15 (+ 2)
% Row 7
\SetRowColor{white}
Select all elements of the first row & matrix{[}1,{]} \tn 
% Row Count 17 (+ 2)
% Row 8
\SetRowColor{LightBackground}
Select 2nd element of 3rd column & matrix{[}2,3{]} \tn 
% Row Count 19 (+ 2)
% Row 9
\SetRowColor{white}
Create matrix with the data on the rows 1, 2, 3 and columns 2, 3, 4. & matrix{[}1:3,2:4{]} \tn 
% Row Count 23 (+ 4)
% Row 10
\SetRowColor{LightBackground}
Average of the matrix elements & mean(matrix\_name) \tn 
% Row Count 25 (+ 2)
% Row 11
\SetRowColor{white}
Summary of Matrix (and other stuff) & \seqsplit{summary(matrix\_name)} \tn 
% Row Count 27 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\SetRowColor{LightBackground}
\mymulticolumn{2}{x{5.377cm}}{{\emph{The argument byrow indicates that the matrix is filled by the rows. If we want the matrix to be filled by the columns, we just place byrow = FALSE}} \newline  \newline {\bf{all data in a matrix should be of the same type. Otherwise, create a data frame}}}  \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}--}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Naming a Matrix}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\# Box office Star Wars (in millions!) \newline new\_hope \textless{}- c(460.998, 314.4) \newline empire\_strikes \textless{}- c(290.475, 247.900) \newline return\_jedi \textless{}- c(309.306, 165.8) \newline  \newline \# Construct matrix \newline star\_wars\_matrix \textless{}- matrix(c(new\_hope, empire\_strikes, return\_jedi), nrow = 3, byrow = TRUE) \newline  \newline \# Vectors region and titles, used for naming \newline region \textless{}- c("US", "non-US") \newline titles \textless{}- c("A New Hope", "The Empire Strikes Back", "Return of the Jedi") \newline  \newline \# Name the columns with region \newline colnames(star\_wars\_matrix) \textless{}- region \newline  \newline \# Name the rows with titles \newline rownames(star\_wars\_matrix) \textless{}- titles \newline  \newline \# Print out star\_wars\_matrix \newline star\_wars\_matrix} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}